IEEE

Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data

Abstract: Semi-supervised learning (SSL) has attracted enormous attention due to its vast potential of mitigating the dependence on large labeled datasets. The latest methods (e.g., FixMatch) use a ...
IEEE

Word Sense Disambiguation Model for Wolaita Language Using Semi-Supervised Learning, Transformer Models, and Explainable AI

Abstract: Human-to-machine interaction has been enhanced by applications, including speech recognition, machine translation, information retrieval, and many natural language processing (NLP) tasks.
GitHub

SemiDFL: A Semi-Supervised Paradigm for Decentralized Federated Learning

SemiDFL introduces the first semi-supervised decentralized federated learning (DFL) framework, addressing the challenges of limited labeled data and non-IID distributions among decentralized clients.
GitHub

Steering Language Model to Stable Speech Emotion Recognition via Contextual Perception and Chain of Thought

To better simulate real-world context, we introduce a new SER test set, Emo-Emilia. Specifically, we apply the automated labeling approach to annotate Emilia, a large-scale multilingual and diverse ...